© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74610
    Prev
    Next
    INDEX
    Explanations

    progress in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -2.02
    /
    -1.88
     an
    -1.79
     any
    -1.50
    蟊
    -1.43
     three
    -1.41
     eight
    -1.40
     for
    -1.38
     these
    -1.38
     one
    -1.36
    POSITIVE LOGITS
    s
    1.94
    </b>
    1.81
    ほんと
    1.66
    TacToe
    1.64
    哽
    1.61
    ほとん
    1.58
    餉
    1.58
    全体的に
    1.55
     protože
    1.55
     praktischen
    1.55
    Activations Density 0.035%

    No Known Activations